Jiaqi Li

RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling

MIRAGE: MULTI-HOP INTERLEAVED REASONING AND RETRIEVAL-GROUNDED EVIDENCE

LIFT: Enhancing Long-Context Reasoning in Large Language Models via Long Input Fine-Tuning

In-Context Editing: Learning Knowledge from Self-Induced Distributions

Optimizing Inference-Time Reasoning in LLMs via Retrieval-Augmented Reflection